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

    Neuronpedia

    INDEX
    Explanations

    truth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -str
    -0.07
    ANGLES
    -0.06
    (surface
    -0.06
    �
    -0.06
     caul
    -0.06
     �
    -0.06
     ImGui
    -0.06
    .radio
    -0.06
     captcha
    -0.06
     Results
    -0.06
    POSITIVE LOGITS
    发生
    0.07
    片
    0.06
    activate
    0.06
    θ
    0.06
     организации
    0.06
    >');↵↵
    0.06
     erotique
    0.06
     تشخیص
    0.06
    ');?>↵
    0.06
     normally
    0.06
    Act Density 0.000%

    No Known Activations