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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dart
    -0.08
     alright
    -0.07
     waiting
    -0.07
     TreeSet
    -0.06
     dvd
    -0.06
    .VERTICAL
    -0.06
    _STORAGE
    -0.06
    Taylor
    -0.06
     след
    -0.06
    dan
    -0.06
    POSITIVE LOGITS
    :flex
    0.06
     ц
    0.06
    inion
    0.06
     cư
    0.06
    emp
    0.06
    gL
    0.06
    gabe
    0.06
    ESIS
    0.06
     بق
    0.06
    üme
    0.06
    Act Density 0.007%

    No Known Activations