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

    Neuronpedia

    INDEX
    Explanations

    Recycle bin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chair
    -0.07
     Officers
    -0.07
     initialState
    -0.07
    oneksi
    -0.07
    .question
    -0.07
    fruit
    -0.07
    工具
    -0.07
    _DELETE
    -0.07
    avier
    -0.07
    udson
    -0.07
    POSITIVE LOGITS
    "]->
    0.07
    References
    0.07
    跷
    0.07
    �
    0.07
    ঙ
    0.07
    нима
    0.07
     mechanism
    0.07
    ዛ
    0.07
    ㎎
    0.06
     origin
    0.06
    Act Density 0.095%

    No Known Activations