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

    Neuronpedia

    INDEX
    Explanations

    flow

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clashed
    -0.09
    瓠
    -0.08
    -size
    -0.07
     nonetheless
    -0.07
    ivalence
    -0.07
    对其真实
    -0.07
     flare
    -0.07
    clarsimp
    -0.07
     vaccinated
    -0.07
     presidency
    -0.06
    POSITIVE LOGITS
    Transition
    0.08
    Recording
    0.07
    ajaran
    0.07
    集成
    0.07
    بن
    0.07
     queer
    0.07
    Walk
    0.07
     jeux
    0.07
    VR
    0.07
    万人
    0.06
    Act Density 0.043%

    No Known Activations