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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avez
    -0.06
    てい
    -0.06
     науков
    -0.06
     penetrating
    -0.06
     Reason
    -0.06
    glass
    -0.06
    _sms
    -0.06
     peptide
    -0.06
    ething
    -0.06
     наших
    -0.06
    POSITIVE LOGITS
     Dien
    0.07
    .POST
    0.07
    _Size
    0.06
    .choices
    0.06
    TP
    0.06
     Troy
    0.06
     센
    0.06
     outings
    0.06
     Sofa
    0.06
     ))↵
    0.06
    Act Density 0.020%

    No Known Activations