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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    proved
    -0.09
    -defined
    -0.08
    beda
    -0.08
    oso
    -0.08
    specified
    -0.08
     นี้
    -0.08
    creased
    -0.08
    arger
    -0.08
    abilidades
    -0.08
    daad
    -0.08
    POSITIVE LOGITS
     antagonist
    0.09
     narrator
    0.09
    .hh
    0.08
     later
    0.08
     interns
    0.08
     skeptical
    0.08
     yngre
    0.08
     mentors
    0.08
     Reception
    0.08
     colleagues
    0.07
    Act Density 0.048%

    No Known Activations