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

    Neuronpedia

    INDEX
    Explanations

    HH

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.79
    Geografía
    -0.78
    ViewFeatures
    -0.77
    +#+#
    -0.75
    InvalidProtocol
    -0.71
     متعلقه
    -0.69
     GenerationType
    -0.67
    expandindo
    -0.66
    ]")]
    -0.66
    TargetException
    -0.65
    POSITIVE LOGITS
     include
    0.52
    then
    0.48
     same
    0.47
    Elsewhere
    0.45
    not
    0.44
    同じく
    0.44
     like
    0.43
     avantages
    0.43
     next
    0.42
     Fieber
    0.42
    Act Density 0.000%

    No Known Activations