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

    Neuronpedia

    INDEX
    Explanations

    lisp let expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ElementException
    0.41
     oído
    0.40
     acquaint
    0.39
     huesos
    0.39
    ﮕ
    0.39
     ಕೂದಲ
    0.38
     doubtless
    0.38
    男孩
    0.38
     noss
    0.38
    SequentialGroup
    0.37
    POSITIVE LOGITS
    *
    0.42
    filt
    0.38
     originally
    0.37
     "
    0.36
     Blocking
    0.36
     ecol
    0.35
     નથી
    0.35
    endas
    0.35
    zec
    0.35
     Slam
    0.35
    Act Density 0.001%

    No Known Activations