Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terminology associated with surpluses and excesses in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    excess or surplus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.64
     włosów
    -0.56
    HostException
    -0.53
    ResumeLayout
    -0.53
    PhysRevLett
    -0.51
     IFTT
    -0.46
     invokingState
    -0.46
    contentLoaded
    -0.45
    存于互联网档案馆
    -0.45
    LookAnd
    -0.45
    POSITIVE LOGITS
     surplus
    0.96
     excess
    0.83
     spare
    0.82
    excess
    0.78
     Excess
    0.77
    Excess
    0.76
     Surplus
    0.75
    spare
    0.68
     surpluses
    0.67
    Spare
    0.60
    Act Density 0.155%

    No Known Activations