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

    Neuronpedia

    INDEX
    Explanations

    prolific

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     graduation
    -0.07
     segment
    -0.06
    Shapes
    -0.06
     Theta
    -0.06
     Lambda
    -0.06
     frail
    -0.06
    preserve
    -0.06
    .ar
    -0.06
     Transformation
    -0.06
    ruits
    -0.06
    POSITIVE LOGITS
     Virgin
    0.07
    ілля
    0.07
    ीमत
    0.07
     avid
    0.07
    maxlength
    0.07
     MAKE
    0.06
     �
    0.06
     百
    0.06
    .FirstName
    0.06
     `;↵
    0.06
    Act Density 0.008%

    No Known Activations