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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inha
    -0.07
    133
    -0.06
     Reynolds
    -0.06
    ponents
    -0.06
    .alignment
    -0.06
     jclass
    -0.06
     survives
    -0.06
    OwnerId
    -0.05
    72
    -0.05
     Collider
    -0.05
    POSITIVE LOGITS
     verifica
    0.08
    owania
    0.07
     overs
    0.07
    	callback
    0.07
     venir
    0.07
     keeper
    0.07
    θε
    0.06
     Specifically
    0.06
    nb
    0.06
    (SC
    0.06
    Act Density 0.021%

    No Known Activations