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

    Neuronpedia

    INDEX
    Explanations

    z

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    entimes
    -0.07
    spent
    -0.07
     původ
    -0.06
     decryption
    -0.06
     mount
    -0.06
     layout
    -0.06
    ของผ
    -0.06
     гор
    -0.06
     capacity
    -0.06
    해서
    -0.06
    POSITIVE LOGITS
    ILED
    0.07
    ние
    0.07
     Wu
    0.07
    orable
    0.06
    Carol
    0.06
    Unt
    0.06
    łe
    0.06
    lak
    0.06
    LEM
    0.06
     اون
    0.06
    Act Density 0.000%

    No Known Activations