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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _perms
    -0.06
     contenido
    -0.06
     Psi
    -0.06
    想到
    -0.06
    \Traits
    -0.06
    $b
    -0.06
    .Car
    -0.05
    alyzed
    -0.05
    _merged
    -0.05
    _wheel
    -0.05
    POSITIVE LOGITS
     Barrett
    0.08
     prayer
    0.07
    _sentences
    0.07
     �
    0.07
    fm
    0.06
    throat
    0.06
    の子
    0.06
    Noise
    0.06
     NSLayoutConstraint
    0.06
     Nashville
    0.06
    Act Density 0.000%

    No Known Activations