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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    207
    -0.07
    141
    -0.06
    яви
    -0.06
     After
    -0.06
    409
    -0.06
    122
    -0.06
    fü
    -0.06
    άνω
    -0.06
    Following
    -0.06
     이미
    -0.06
    POSITIVE LOGITS
    <c
    0.07
     MainAxisAlignment
    0.07
     seedu
    0.07
     phường
    0.06
     Gew
    0.06
    schools
    0.06
    _LS
    0.06
    �
    0.06
    @NoArgsConstructor
    0.06
    cart
    0.06
    Act Density 0.321%

    No Known Activations