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

    Neuronpedia

    INDEX
    Explanations

    study research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _thresh
    -0.07
     engine
    -0.07
     wash
    -0.07
     Gen
    -0.07
     War
    -0.06
     engines
    -0.06
     kỳ
    -0.06
     ldap
    -0.06
     Spirit
    -0.06
     terre
    -0.06
    POSITIVE LOGITS
    OCUMENT
    0.07
    월까지
    0.06
    Toast
    0.06
    taient
    0.06
     TreeSet
    0.06
    _enqueue
    0.06
    统计
    0.06
    قام
    0.06
     нескольких
    0.06
    =&
    0.06
    Act Density 0.041%

    No Known Activations