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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝓯
    -0.08
    ’acc
    -0.07
    קום
    -0.07
     Paths
    -0.07
    puted
    -0.07
    غذي
    -0.07
    דור
    -0.07
    OME
    -0.07
    ڑ
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    Begin
    0.07
    EncodingException
    0.07
     assurances
    0.07
     tặng
    0.07
     comprar
    0.07
     actividad
    0.07
    ชาว
    0.07
    .permission
    0.07
    最も
    0.06
     cmake
    0.06
    Act Density 0.009%

    No Known Activations