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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wat
    -0.07
    �
    -0.06
    п
    -0.06
     HH
    -0.06
    _PL
    -0.06
    may
    -0.06
     contraseña
    -0.06
    ?t
    -0.06
     Riders
    -0.06
     HDMI
    -0.06
    POSITIVE LOGITS
     фун
    0.06
    Honestly
    0.06
    _PROFILE
    0.06
     Pompe
    0.06
     prem
    0.06
     activations
    0.06
    arem
    0.06
     ชนะ
    0.06
     cardinal
    0.06
    .getName
    0.06
    Act Density 0.022%

    No Known Activations