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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     depicted
    -0.07
    .Caption
    -0.07
     Assass
    -0.07
    addChild
    -0.07
     towers
    -0.07
    ría
    -0.07
    aised
    -0.07
    animal
    -0.07
     <?
    -0.07
    台风
    -0.07
    POSITIVE LOGITS
     Competitive
    0.07
     العدو
    0.07
     edits
    0.07
    _COMP
    0.07
     LOGIN
    0.07
     FR
    0.07
    INIT
    0.07
    CNT
    0.07
     IMO
    0.06
    をしている
    0.06
    Act Density 0.005%

    No Known Activations