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

    Neuronpedia

    INDEX
    Explanations

    work emails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hold
    -0.06
    appen
    -0.06
    omy
    -0.06
     acos
    -0.06
     enchanted
    -0.06
    icare
    -0.06
     vectors
    -0.06
    sword
    -0.06
    ictory
    -0.06
    othermal
    -0.06
    POSITIVE LOGITS
    Од
    0.07
    INS
    0.07
    LES
    0.06
     relocate
    0.06
    짓
    0.06
    _quotes
    0.06
    ━━━━
    0.06
     relocated
    0.06
    undred
    0.06
     swagger
    0.06
    Act Density 0.095%

    No Known Activations