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

    Neuronpedia

    INDEX
    Explanations

    trial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     тран
    -0.07
     din
    -0.07
    (holder
    -0.06
    (`${
    -0.06
     बह
    -0.06
     operates
    -0.06
    .dgv
    -0.06
    _estado
    -0.06
    undi
    -0.06
    _Private
    -0.06
    POSITIVE LOGITS
     strife
    0.07
    들도
    0.06
     vriend
    0.06
    пи
    0.06
     Clo
    0.06
     Directions
    0.06
     tieten
    0.06
     Warrior
    0.06
     Final
    0.06
     fleeing
    0.06
    Act Density 0.006%

    No Known Activations