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

    Neuronpedia

    INDEX
    Explanations

    pause

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BANK
    -0.07
    #!
    -0.07
     ContentValues
    -0.06
     filles
    -0.06
     commodity
    -0.06
     Rog
    -0.06
    .GroupLayout
    -0.06
     <%=
    -0.06
     Et
    -0.06
    Alternative
    -0.06
    POSITIVE LOGITS
     denominator
    0.07
    -or
    0.07
    .Magenta
    0.06
     ErrorMessage
    0.06
    URRENT
    0.06
    ldkf
    0.06
    씀
    0.06
     στην
    0.06
    遭
    0.06
     offence
    0.06
    Act Density 0.005%

    No Known Activations