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

    Neuronpedia

    INDEX
    Explanations

    px

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ould
    -0.07
    .blue
    -0.07
    ush
    -0.07
    𝐉
    -0.07
    routes
    -0.07
    زار
    -0.07
    inded
    -0.07
     forc
    -0.07
    ckpt
    -0.06
     overhe
    -0.06
    POSITIVE LOGITS
    _aw
    0.07
    =\"/
    0.07
     Именно
    0.07
    合成
    0.07
    💳
    0.07
    杀人
    0.06
    纵观
    0.06
     academic
    0.06
    .delta
    0.06
    Slave
    0.06
    Act Density 0.001%

    No Known Activations