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

    Neuronpedia

    INDEX
    Explanations

    necess

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Startup
    -0.07
     Fot
    -0.07
    urray
    -0.07
     ow
    -0.06
     Dol
    -0.06
     preferably
    -0.06
    [h
    -0.06
     Suicide
    -0.06
     Su
    -0.06
    ior
    -0.06
    POSITIVE LOGITS
    _REFERER
    0.07
    illusion
    0.07
     exerc
    0.06
     gere
    0.06
    !=↵
    0.06
    CESS
    0.06
    719
    0.06
    ffc
    0.06
    /em
    0.06
    .getError
    0.06
    Act Density 0.005%

    No Known Activations