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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avoir
    -0.06
     negate
    -0.06
    erate
    -0.06
     lays
    -0.06
     Collapse
    -0.06
     Rico
    -0.06
    -vector
    -0.06
     capture
    -0.06
     Grupo
    -0.06
    Cipher
    -0.06
    POSITIVE LOGITS
    PIPE
    0.07
    _RSA
    0.06
    expects
    0.06
    лених
    0.06
     evolved
    0.06
    �
    0.06
     فو
    0.06
     Hard
    0.06
    ’ят
    0.06
     đăng
    0.06
    Act Density 0.003%

    No Known Activations