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

    Neuronpedia

    INDEX
    Explanations

    secure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     skin
    -0.07
    睛
    -0.07
     mise
    -0.07
    嬗
    -0.07
    اعتماد
    -0.07
    thetic
    -0.07
    說
    -0.06
     расположен
    -0.06
    侦查
    -0.06
    究
    -0.06
    POSITIVE LOGITS
    (Attribute
    0.07
    決め
    0.07
     zdarma
    0.06
     Clim
    0.06
    ☢
    0.06
    �
    0.06
    栗
    0.06
    苉
    0.06
    流产
    0.06
    nym
    0.06
    Act Density 0.078%

    No Known Activations