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

    Neuronpedia

    INDEX
    Explanations

    knowing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mix
    -0.07
     Flash
    -0.07
    ительное
    -0.07
    كي
    -0.06
    یره
    -0.06
    Construct
    -0.06
    756
    -0.06
     suspicion
    -0.06
    Defaults
    -0.06
    Appearance
    -0.06
    POSITIVE LOGITS
     gerne
    0.07
     samt
    0.07
    _FT
    0.07
    eted
    0.06
    (Label
    0.06
     �
    0.06
    adx
    0.06
    ,:,:
    0.06
     gj
    0.06
    xbd
    0.06
    Act Density 0.029%

    No Known Activations