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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (PHP
    -0.07
    ("\
    -0.06
    uitive
    -0.06
     chiếc
    -0.06
    rylic
    -0.06
     �
    -0.06
     реч
    -0.06
    Curve
    -0.06
    .Body
    -0.06
     malloc
    -0.06
    POSITIVE LOGITS
    ären
    0.07
     dem
    0.07
     bomb
    0.06
     worried
    0.06
    ano
    0.06
     crossed
    0.06
    ायन
    0.06
     bombs
    0.06
    znam
    0.06
    depending
    0.06
    Act Density 0.060%

    No Known Activations