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

    Neuronpedia

    INDEX
    Explanations

    causality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /body
    -0.08
    \
↵
    -0.06
     wsp
    -0.06
     certificate
    -0.06
    _L
    -0.06
    )”
    -0.06
    Pale
    -0.06
     olds
    -0.06
     concussion
    -0.06
    .Cell
    -0.06
    POSITIVE LOGITS
     області
    0.07
     رابطه
    0.07
     [\
    0.07
    одатель
    0.06
     Hawaiian
    0.06
     �
    0.06
    ує
    0.06
    pling
    0.06
    mapper
    0.06
     airst
    0.06
    Act Density 0.062%

    No Known Activations