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
    _VF
    -0.07
     другого
    -0.06
    odom
    -0.06
    یره
    -0.06
    .old
    -0.06
    ]()↵
    -0.06
     Were
    -0.06
    ráci
    -0.06
     cwd
    -0.06
     sensational
    -0.06
    POSITIVE LOGITS
     �
    0.07
    .l
    0.07
     Singular
    0.07
    =models
    0.06
    emode
    0.06
    Intermediate
    0.06
    毕业
    0.06
     intermediate
    0.06
     autofocus
    0.06
     Apr
    0.06
    Act Density 0.068%

    No Known Activations