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

    Neuronpedia

    INDEX
    Explanations

    delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gör
    -0.07
     hover
    -0.07
    TextEdit
    -0.07
    𝕣
    -0.07
     vacation
    -0.07
     changing
    -0.06
    놓
    -0.06
    .setBounds
    -0.06
     Gardner
    -0.06
    ittel
    -0.06
    POSITIVE LOGITS
    不安
    0.08
    母校
    0.07
    [js
    0.07
    _rhs
    0.07
     Cobra
    0.07
    音
    0.07
    ><
    0.07
     parentId
    0.07
     parach
    0.07
    得以
    0.07
    Act Density 0.085%

    No Known Activations