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

    Neuronpedia

    INDEX
    Explanations

    Dodging and agility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     penis
    -0.07
    uft
    -0.06
     moral
    -0.06
    вест
    -0.06
    vn
    -0.06
     MLA
    -0.06
     smlouvy
    -0.06
    rts
    -0.06
     aura
    -0.06
     Christie
    -0.06
    POSITIVE LOGITS
    rawing
    0.07
     outcome
    0.07
    ,’’
    0.06
    ricane
    0.06
    urniture
    0.06
    geometry
    0.06
    นว
    0.06
    habi
    0.06
     randomness
    0.06
     expecting
    0.06
    Act Density 0.021%

    No Known Activations