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

    Neuronpedia

    INDEX
    Explanations

    ol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    े,
    -0.07
    -й
    -0.06
    ูม
    -0.06
    ši
    -0.06
    −
    -0.06
     Гор
    -0.06
    四
    -0.06
     →
    -0.06
     Hmm
    -0.06
    minecraft
    -0.06
    POSITIVE LOGITS
     af
    0.07
     ripple
    0.06
     competent
    0.06
     award
    0.06
     DY
    0.06
     ord
    0.06
     enc
    0.06
     voz
    0.06
    icer
    0.06
     Krishna
    0.06
    Act Density 0.017%

    No Known Activations