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

    Neuronpedia

    INDEX
    Explanations

    actions will be taken

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kritis
    0.45
     hairy
    0.38
     exhaust
    0.37
     overcame
    0.37
     critique
    0.35
     obvi
    0.35
     overcome
    0.34
     kritik
    0.34
     fournis
    0.34
     maxim
    0.34
    POSITIVE LOGITS
     escalate
    0.85
     relay
    0.85
     relayed
    0.80
     escal
    0.73
     relays
    0.72
     escalated
    0.71
    escal
    0.70
     escalation
    0.70
     escalating
    0.69
     Escal
    0.69
    Act Density 0.012%

    No Known Activations