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

    Neuronpedia

    INDEX
    Explanations

    animal experiments

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of experimental animals being sacrificed (or killed) and the associated timing.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     brewed
    -0.07
    *p
    -0.07
    urar
    -0.06
    *M
    -0.06
    _Level
    -0.06
     söyley
    -0.06
     inhal
    -0.06
    Σ
    -0.06
    *c
    -0.06
    HTTPHeader
    -0.06
    POSITIVE LOGITS
    '},
↵
    0.08
     verdade
    0.06
     der
    0.06
     onSave
    0.06
     incluso
    0.06
     GFX
    0.06
     JSONArray
    0.06
     afore
    0.06
     Söz
    0.06
    scoped
    0.06
    Act Density 0.005%

    No Known Activations