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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _combo
    -0.07
     sco
    -0.06
     shine
    -0.06
     makin
    -0.06
     kan
    -0.06
    rbrakk
    -0.06
    true
    -0.06
    >e
    -0.06
    油
    -0.06
     mist
    -0.06
    POSITIVE LOGITS
     convoy
    0.07
     anymore
    0.07
     any
    0.07
     Garn
    0.07
    üy
    0.06
    European
    0.06
    toList
    0.06
     panicked
    0.06
     Maxim
    0.06
     Ay
    0.06
    Act Density 0.064%

    No Known Activations