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

    Neuronpedia

    INDEX
    Explanations

    mental health

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hat
    -0.08
     regs
    -0.07
    uelles
    -0.07
    lém
    -0.07
    ères
    -0.06
    от
    -0.06
     üretim
    -0.06
    llx
    -0.06
     가정
    -0.06
     ptr
    -0.06
    POSITIVE LOGITS
    .SH
    0.07
     Psychological
    0.07
    Fl
    0.07
     Kro
    0.06
    amer
    0.06
     zoom
    0.06
     Subtract
    0.06
    ountries
    0.06
    Adv
    0.06
    ousel
    0.06
    Act Density 0.014%

    No Known Activations