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

    Neuronpedia

    INDEX
    Explanations

    Abstract concepts with suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Every
    -0.07
    _input
    -0.07
     assure
    -0.06
    subscribe
    -0.06
     ruins
    -0.06
    222
    -0.06
    Every
    -0.06
    посеред
    -0.06
     every
    -0.06
     Intersection
    -0.06
    POSITIVE LOGITS
     Sın
    0.06
    (trans
    0.06
    Spe
    0.06
    _nf
    0.06
    (",
    0.06
     kond
    0.06
     aup
    0.06
    _asm
    0.06
     compét
    0.06
    =default
    0.06
    Act Density 0.056%

    No Known Activations